﻿ 基于数据挖掘的船舶通信网络信号传输数学模型
 舰船科学技术  2023, Vol. 45 Issue (19): 169-172    DOI: 10.3404/j.issn.1672-7649.2023.19.031 PDF

A mathematical model for signal transmission in ship communication network based on data mining
ZHAO Lin
Department of Mathematics and Information Engineering, Liaocheng University Dongchang College, Liaocheng 252000, China
Abstract: In order to ensure the safety and speed of signal transmission in ship communication networks, a mathematical model for signal transmission in ship communication networks based on data mining is studied. After collecting the signal strength fingerprint of the ship communication network, this model will establish a ship communication network energy consumption model based on it. The current ship communication network energy consumption will be obtained through this model, and then based on this energy consumption, the optimal communication link of the ship communication network will be selected according to game theory. According to this optimal communication link, a convolutional neural network in data mining algorithms will be used to construct a mathematical model for ship communication network signal transmission, Utilize this model to achieve signal transmission in ship communication networks. The experimental results show that the model can effectively transmit signals from ship to ship communication networks, with less transmission time and higher residual energy of network nodes. The application effect is good.
Key words: data mining     ship communication network     signal transmission     mathematical model     convolutional neural network
0 引　言

1 船舶通信网络信号传输数学模型 1.1 船舶通信网络采集信号强度指纹

 ${R_{{F_P}}} = \frac{1}{N}\sum\limits_{i = 1}^N {{R_{{S_{{P_i}}}}}}。$ (1)

1.2 船舶通信网络能耗模型构建

${E_{TX}}({G_{Trans}},{G_{CON}},M)$ 表示船舶通信网络节点处于发送状态的能耗，其中 $M$ 为节点发送有效信号数据包个数， ${G_{Trans}}$ 为发送信号数据包周期， ${G_{CON}}$ 为信号处理时长，该能耗计算公式如下：

 $\begin{split} &{E_{TX}}({G_{Trans}},{G_{CON}},M) = M \times V \times {R_{{F_P}}} \times \left[ {I_{TX}}{G_{TX}} +\right.\\ &\left. {I_{CON}}{G_{CON}} + {I_{RX}}({G_{Trans}} - {G_{TX}} - {G_{CON}}) \right]。\end{split}$ (2)

${E_{RX}}({G_{Trans}},{G_{CON1}},M)$ 表示传感器发送状态能耗，其中 ${G_{CON1}}$ 表示信号处理阶段时长，则该阶段能耗表达式如下：

 $\begin{gathered} {E_{RX}}({G_{Trans}},{G_{CON1}},M) = M \times V \times \\ \left\{ \begin{gathered} n({I_{ACK}}{G_{ACK}} + {I_{CON1}}{G_{CON1}}) + \\ {I_{RX1}}\left[ {{G_{Trans}} - n({G_{ACK}} + {G_{CON1}})} \right] \\ \end{gathered} \right\}。\\ \end{gathered}$ (3)

1.3 基于博弈论的最优通信链路选择

 $\tau (i,j) = \frac{{\sigma {E_i}}}{{{E_j}}} - \frac{{(1 - \sigma ){F_{i,j}}}}{{{{\bar F}_{i,j}}}} - \eta {U_{(i,Sink)}} - \frac{{\rho {B_i}}}{{{{\bar B}_{(i,nei)}}}}。$ (4)

 ${F_{(i,j)}} = \varepsilon {({10^{ - (\lambda - 37)/40}})^4} 。$ (5)

1.4 数据挖掘算法的网络信号传输数学模型构建

 图 1 网络信号传输数学模型结构 Fig. 1 Mathematical model structure of network signal transmission

$H$ 为模型信道矩阵， $Y$ 为接收端接收到的信道信号，计算公式如下：

 $Y = HD + Q 。$ (6)

 $S' = g(Y) 。$ (7)

2 结果与分析

 图 2 通信传输节点能量 Fig. 2 Energy of communication transmission nodes

 图 3 船舶通信网络信号传输丢包率 Fig. 3 Packet loss rate of signal transmission in ship communication network
3 结　语

 [1] 郭旭飞. 固体火箭发动机多层结构超声信号传输的数学模型[J]. 弹箭与制导学报, 2022, 42(1): 38-41,48. GUO Xu-fei. mathematical model of ultrasonic signal transmission in solid rocket motor multilayer structure[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2022, 42(1): 38-41,48. [2] 程天相, 王剑平, 金建辉. 水下极板电场通信传输模型研究[J]. 重庆邮电大学学报(自然科学版), 2023, 35(1): 31-39. CHENG Tian-xiang, WANG Jian-ping, JIN Jian-hui. Study on electric field communication transmission model of underwater polar plate[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2023, 35(1): 31-39. [3] 佘维, 霍丽娟, 刘炜, 等. 一种可隐藏敏感文档和发送者身份的区块链隐蔽通信模型[J]. 电子学报, 2022, 50(4): 1002-1013. SHE Wei, HUO Li-juan, LIU Wei, et al. A blockchain-based covert communication model for hiding sensitive documents and sender identity[J]. Acta Electronica Sinica, 2022, 50(4): 1002-1013. [4] 胡金锁, 周国印, 张迎, 等. 联合战术通信网络中的无线协同传输技术[J]. 兵工学报, 2022, 43(10): 2649-2656. HU Jin-suo, ZHOU Guo-yin, ZHANG Ying, et al. Wireless cooperative transmission in joint tactical communication network[J]. Acta Armamentarii, 2022, 43(10): 2649-2656. [5] 江沸菠, 彭于波, 董莉. 面向6G的深度图像语义通信模型[J]. 通信学报, 2023, 44(3): 198-208. JIANG Fei-bo, PENG Yu-bo, DONG Li. Deep image semantic communication model for 6G[J]. Journal on Communications, 2023, 44(3): 198-208. [6] 李明时, 马跃, 尹震宇, 等. 一种多重冗余的工业物联网智能产线安全通信模型设计[J]. 小型微型计算机系统, 2021, 42(3): 621-626. LI Ming-shi, MA Yue, YIN Zhen-yu, et al. Design of a multi-redundant secure communication model for intelligent production line of industrial Internet of Things[J]. Journal of Chinese Computer Systems, 2021, 42(3): 621-626. [7] 王浩同, 刘白林, 刘智平, 等. 基于区块链的无人机集群抗干扰通信模型[J]. 火力与指挥控制, 2022, 47(1): 72-79. WANG Hao-tong, LIU Bai-lin, LIU Zhi-ping, et al. Anti-interference communication model of drone cluster based on blockchain[J]. Fire Control & Command Control, 2022, 47(1): 72-79.